A Deep Learning Classification Scheme for PolSAR Image Based on Polarimetric Features

Round 1

Reviewer 1 Report

See the attachment file.

Comments for author File: Comments.pdf

Minor editing of English language required.

Author Response

The authors, above all, would like to thank you for your comments to help to improve the manuscript. All the comments are seriously considered and the manuscript is refined correspondingly. We thank you for taking the time to review the manuscript and appreciate all your comments and suggestions. Based on the instructions provided in your letter, we have submitted the revised manuscript with revisions highlighted in a different color (red).

Please refer to the attachment for details

Author Response File: Author Response.docx

Reviewer 2 Report

This article focuses on a method to perform polarimetric classification of SAR images using artificial intelligence.
The article appears to be technically correct, but there are some things that need to be modified/improved.
The Abstract is too long. The issue is not well focused, so it needs to be modified ad hoc to make it more understandable.
In the current version, Fig. 1 is not consistent in the sense that the author does not understand its meaning at all. Every figure that you insert must have the necessary information to be fully comprehensible, at minimum effort. Therefore, first of all it must be enlarged and then the dimensions of the matrices and tensors are not indicated. The results include classification maps that are not explained well.
The formulas need to be adjusted, they are all misaligned, I honestly cannot imagine that the manuscript was submitted like this, without at least checking the graphics. As far as the contents are concerned, more crucial information regarding the analytical model needs to be added, in this condition it is highly unlikely that the work can at least be sent forward for further revision.
Experimental results may be fine, as there are ground truths.  

No issue detected

Author Response

The authors, above all, would like to thank you for your comments to help to improve the manuscript. All the comments are seriously considered and the manuscript is refined correspondingly. We thank you for taking the time to review the manuscript and appreciate all your comments and suggestions. Based on the instructions provided in your letter, we have submitted the revised manuscript with revisions highlighted in a different color (red).

Please refer to the attachment for details

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

Dear Author, in my personal opinion this article can be accepted in the present form.

Accepted